One-shot federated learning (OSFL) reduces the communication cost and privacy risks of iterative federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve robust performance on real-world domains such as medical imaging, or are inefficient when handling non-IID (Independent and Identically Distributed) data. To address these limitations, we introduce FALCON, a framework that enhances the effectiveness of OSFL over non-IID image data. The core idea of FALCON is […]

Ver mais

Sunday panic attacks are the hidden reality for many data leaders. This story explores the “savior complex,” the cycle of burnout, and why we struggle to find rhythm. It challenges the idea that better tools can fix personal patterns and asks the hard question: Can we do transformational work without destroying ourselves? You aren’t broken; you just care too much without boundaries.

Ver mais

arXiv:2602.07195v1 Announce Type: new Abstract: Interactive computational notebooks (e.g., Jupyter notebooks) are widely used in machine learning engineering (MLE) to program and share end-to-end pipelines, from data preparation to model training and evaluation. However, environment erosion-the rapid evolution of hardware and software ecosystems for machine learning-has rendered many published MLE notebooks non-reproducible in contemporary environments, hindering code reuse and scientific progress. To quantify this gap, we study 12,720 notebooks mined from 79 popular Kaggle competitions: only 35.4% remain […]

Ver mais

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the constitution) specified in natural language. However, it is unclear how to fairly determine this constitution with widespread stakeholder input. In this work we propose Grounded Constitutional AI (GCAI), a unified framework for generating constitutions of principles that are representative of both users’ […]

Ver mais

arXiv:2601.19918v1 Announce Type: new Abstract: Hallucinations in Large Language Models (LLMs), i.e., the tendency to generate plausible but non-factual content, pose a significant challenge for their reliable deployment in high-stakes environments. However, existing hallucination detection methods generally operate under unrealistic assumptions, i.e., either requiring expensive intensive sampling strategies for consistency checks or white-box LLM states, which are unavailable or inefficient in common API-based scenarios. To this end, we propose a novel efficient zero-shot metric called Lowest Span Confidence […]

Ver mais

arXiv:2411.02694v2 Announce Type: replace Abstract: Point processes are widely used statistical models for continuous-time discrete event data, such as medical records, crime reports, and social network interactions, to capture the influence of historical events on future occurrences. In many applications, however, event times are not observed exactly, motivating the need to incorporate time uncertainty into point process modeling. In this work, we introduce a framework for modeling time-uncertain self-exciting point processes, known as Hawkes processes, possibly defined over […]

Ver mais

India’s AQI crisis sees no signs of abating. All across northern India, the winter season sees the AQI stay in the very hazardous category for months together across the big cities, small towns, and even villages of North India. AQI readings above 400 are routine, and one has come to regard a 150 AQI, which constitutes the poor category, as pretty much normal and par for the course. The fact that the high AQI levels have started getting […]

Ver mais

arXiv:2601.18803v1 Announce Type: new Abstract: This paper proposes a task-agnostic discovery layer for multivariate time series that constructs a relational hypothesis graph over entities without assuming linearity, stationarity, or a downstream objective. The method learns window-level sequence representations using an unsupervised sequence-to-sequence autoencoder, aggregates these representations into entity-level embeddings, and induces a sparse similarity network by thresholding a latent-space similarity measure. This network is intended as an analyzable abstraction that compresses the pairwise search space and exposes candidate […]

Ver mais

The algebraic analysis of linear code parameters reveals deep connections with cryptographic constructions, including the information dispersal algorithms (IDAs) and secret-sharing schemes. In this work, we propose an algebraic method for constructing bases of binary linear codes from subsets of codewords selected according to their generalized Hamming weights (GHWs). The approach employs a degree-compatible monomial ordering on the polynomial ring F2[x1, . . . , xn] and imposes the conditions d1(C) = 1 and dk (C) = n. […]

Ver mais